© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 61058
    Prev
    Next
    INDEX
    Explanations

    slip bands

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_11_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     nổi
    0.49
    ى
    0.48
    త్ర
    0.48
    òa
    0.47
    тер
    0.47
    ੇ
    0.47
    те
    0.46
    डर
    0.45
    ता
    0.44
     पो
    0.44
    POSITIVE LOGITS
    Chlor
    0.61
    chlor
    0.58
     Chirurg
    0.58
    DeviceId
    0.58
    homotopic
    0.56
     cuz
    0.55
     orchids
    0.55
    쫑
    0.55
    December
    0.54
     legumes
    0.54
    Activations Density 0.000%

    No Known Activations